#支持向量机算法原理及实现
#（一）sklearn中利用SVM算法解决分类问题
import numpy as np
import matplotlib.pyplot as plt

#1-1 多算法融合思想的使用——KNN算法参数寻优
from sklearn.feature_selection import SelectKBest
import numpy as np
import pandas as pd
from sklearn.model_selection import KFold   #交叉验证Kfold方式
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score                  #导入整体模型的准确度
from sklearn.metrics import confusion_matrix                #导入整体模型的混淆矩阵
from sklearn.metrics import precision_score                 #导入整体模型的精准率
from sklearn.metrics import recall_score                    #导入整体模型的召回率
from sklearn.metrics import f1_score
#利用管道pipeline来进行多项式核函数的SVM算法三步—多项式回归特征增加-数据归一化-线性SVM算法
from sklearn.preprocessing import PolynomialFeatures   #输入多项式回归模型
from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline
#导入所需要训练的数据集
finaldata=pd.read_excel("C:/Users/y50014900/Desktop/过程测试_033GRR10L4105623_20200601-20200708_IL_DM_异常检测分类结果.xlsx")
feature=["p1","p2","p3","p4","p5","p6","p7","p8","p9","p10","p11","p12","p13","p14","p15","p16","p17","p18","p19","p20","p21","p22","p23"]
DM_target1=["DM1"]
DM_target2=["DM2"]
x=finaldata.iloc[:,2:71]
print(x)
x=np.array(x)                            #对数据的输入需要进行numpy二维数组的转换和形式统一
y=finaldata[DM_target1].values.ravel()  #将表格中的目标列向量转换为一维的数组，作为目标预测的向量
y=finaldata[DM_target2].values.ravel()

#进行数据的numpy数据形式转换，为算法的数据输入做好准备工作
#首先第一步需要进行数据据标准化处理（线性方式）
'''
from sklearn.preprocessing import StandardScaler
s1=StandardScaler()
s1.fit(x)
x_standard=s1.transform(x)
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)

#1-1导入sklearn中SVM的线性分类算法LinearSVC，处理原有的线性数据
from sklearn.preprocessing import StandardScaler
s1=StandardScaler()
s1.fit(x)
x=s1.transform(x)
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
from sklearn.svm import LinearSVC
s11=LinearSVC(C=1e10) #需要定义超参数C，L1、L2正则化的系数，越大，容错空间越小
#对于多分类问题的实现，需要提交参数penalty=l1/l2（正则化方式）以及multi_class=ovo/ovr（采用何种方式多分类训练）
#LinearSVC默认方式为L2正则化，多分类为ovr模式

s11.fit(x_train,y_train)  #训练数据集训练归一化数据集
print(s11.score(x_test,y_test))

#改变正则化的系数C的大小，C越小，容错空间越大
s12=LinearSVC(C=1) #C变小之后，容错空间增大，会有部分数据区分错误
s12.fit(x_train,y_train)  #训练数据集训练归一化数据集
print(s12.score(x_test,y_test))

#1-2 sklearn中对于非线性数据的svm应用（多项式应用方式）
#SVM使用非线性数据假设的模型-手动添加多项式特征模型
#利用管道pipeline来进行多项式核函数的SVM算法三步—多项式回归特征增加-数据归一化-线性SVM算法
from sklearn.preprocessing import PolynomialFeatures   #输入多项式回归模型
from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
def polyniomailSVC(degree,C=10):  #默认正则化系数C为1
    return Pipeline([("poly",PolynomialFeatures(degree=degree)),
                      ("std_scaler",StandardScaler()),
                      ("LinearSVC",LinearSVC(C=C))
                    ])
for i in range(1,3):
    for C in range(1,10):
        p=polyniomailSVC(degree=i,C=C)  #使用三次的多项式特征进行模型的训练
        p.fit(x_train,y_train)
        print(p.score(x_test,y_test))



#1-3 使用自带的多项式核函数的SVM，将数据先直接转换为多项式的多维特征,和传统的多项式特征不同
#2直接利用sklearn中自带的多项式核函数SVM算法，可以自动添加多项式的特征，主要的参数kernel="poly"
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
from sklearn.svm import SVC
def polynomialkernelSVC(degree,C=1.0):
    return Pipeline(
        [
            ("std_canler",StandardScaler()),
            ("kernelsvc",SVC(kernel="poly",degree=degree,C=C))
        ]
    )
for i in range(1,5):
    for j in range(1,10):
        p1=polynomialkernelSVC(degree=i,C=j)
        p1.fit(x_train,y_train)
        print(p1.score(x_test,y_test))
'''

#1-4 高斯核函数的SVM算法的使用-非线性数据训练模型
#调用sklearn中的高斯核函数RBF核（超参数主要是gamma）决定了模型的复杂度，gamma越高，越过拟合
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
import numpy as np
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
def RBFkernelSVC(gamma):
    return Pipeline([
        ("std",StandardScaler()),
        ("svc",SVC(kernel="rbf",gamma=gamma))
    ])
for i in np.arange(0.1,10,1):
    sv=RBFkernelSVC(gamma=i)
    sv.fit(x_train,y_train)
    print(sv.score(x_test,y_test))